Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1134 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.4612. Min Act: -0.1700

Data Index: 3894697 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3909. Min Act: -0.1700

Data Index: 3977294 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3933. Min Act: -0.1700

Data Index: 6763488 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.4071. Min Act: -0.1700

Data Index: 8248927 (Open Web Text)

Max Activating Token Index: 750

Text #4

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3521. Min Act: -0.1700

Data Index: 2229766 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3442. Min Act: -0.1700

Data Index: 5985348 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3451. Min Act: -0.1700

Data Index: 8392240 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3344. Min Act: -0.1700

Data Index: 7342606 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3314. Min Act: -0.1700

Data Index: 3804437 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3437. Min Act: -0.1700

Data Index: 5866808 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3474. Min Act: -0.1700

Data Index: 8168836 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3375. Min Act: -0.1700

Data Index: 820877 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3230. Min Act: -0.1700

Data Index: 3751754 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3322. Min Act: -0.1700

Data Index: 5491031 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3288. Min Act: -0.1700

Data Index: 7562338 (Open Web Text)

Max Activating Token Index: 12

Text #15

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3214. Min Act: -0.1700

Data Index: 5531680 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3216. Min Act: -0.1700

Data Index: 5383937 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3156. Min Act: -0.1700

Data Index: 124956 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3124. Min Act: -0.1700

Data Index: 5413004 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.4612. Min Range: -3.4612

Max Act: 3.3118. Min Act: -0.1700

Data Index: 7061796 (Open Web Text)

Max Activating Token Index: 18